Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1423 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0595. Min Act: -0.0005

Data Index: 1126325 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0005

Data Index: 1157517 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0563. Min Act: -0.0005

Data Index: 309397 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0541. Min Act: -0.0005

Data Index: 805274 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0509. Min Act: -0.0005

Data Index: 917196 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0508. Min Act: -0.0005

Data Index: 462445 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0489. Min Act: -0.0005

Data Index: 716501 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0511. Min Act: -0.0005

Data Index: 479589 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0477. Min Act: -0.0005

Data Index: 749421 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0431. Min Act: -0.0005

Data Index: 335039 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0481. Min Act: -0.0005

Data Index: 429495 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0460. Min Act: -0.0005

Data Index: 631479 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0454. Min Act: -0.0005

Data Index: 1063635 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0476. Min Act: -0.0005

Data Index: 764378 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0459. Min Act: -0.0005

Data Index: 1120146 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0471. Min Act: -0.0005

Data Index: 51846 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0432. Min Act: -0.0005

Data Index: 163667 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0458. Min Act: -0.0005

Data Index: 81155 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0480. Min Act: -0.0005

Data Index: 556771 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0447. Min Act: -0.0005

Data Index: 266734 (C4 (Web Text))

Max Activating Token Index: 582